DocumentCode :
3672467
Title :
Spherical embedding of inlier silhouette dissimilarities
Author :
Etai Littwin;Hadar Averbuch-Elor;Daniel Cohen-Or
Author_Institution :
Tel-Aviv University, Israel
fYear :
2015
fDate :
6/1/2015 12:00:00 AM
Firstpage :
3855
Lastpage :
3863
Abstract :
In this paper, we introduce a spherical embedding technique to position a given set of silhouettes of an object as observed from a set of cameras arbitrarily positioned around the object. Our technique estimates dissimilarities among the silhouettes and embeds them directly in the rotation space SO(3). The embedding is obtained by an optimization scheme applied over the rotations represented with exponential maps. Since the measure for inter-silhouette dissimilarities contains many outliers, our key idea is to perform the embedding by only using a subset of the estimated dissimilarities. We present a technique that carefully screens for inlier-distances, and the pairwise scaled dissimilarities are embedded in a spherical space, diffeomorphic to SO(3). We show that our method outperforms spherical MDS embedding, demonstrate its performance on various multi-view sets, and highlight its robustness to outliers.
Keywords :
"Cameras","Robustness","Sparse matrices","Three-dimensional displays","Optimization","Correlation","Manifolds"
Publisher :
ieee
Conference_Titel :
Computer Vision and Pattern Recognition (CVPR), 2015 IEEE Conference on
Electronic_ISBN :
1063-6919
Type :
conf
DOI :
10.1109/CVPR.2015.7299010
Filename :
7299010
Link To Document :
بازگشت